functionalized things

[phrases.git] / extract.py

diff --git a/extract.py b/extract.py
index a454569a2eebff59cb883c512b389bd7bb98434b..833594da483748f0608acaa5c143e88249d007e9 100755 (executable)
--- a/extract.py
+++ b/extract.py
@@ -1,23 +1,64 @@
 #!/usr/bin/env python3
-# Tool to extract famous phrases from wikipedia
-from bs4 import BeautifulSoup
+# Extract Latin famous phrases from wikipedia
+# Armaan Bhojwani 2020
+
+import argparse
+import sqlite3
 import requests
+from bs4 import BeautifulSoup
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description="Generate SQLite db of Latin famous phrases from Wikipedia.")
+    parser.add_argument("-o", "--output",
+                       default="phrases.db",
+                       help="set custom output file location")
+    return parser.parse_args()
+
+def get_html(url):
+    print("downloading webpage")
+    return BeautifulSoup(requests.get(url).content, "html.parser")
 
-url = 'https://en.wikipedia.org/wiki/List_of_Latin_phrases_(full)'
-response = requests.get(url)
-html = response.content
+def prep_database(c):
+    print("prepping database")
+    c.execute("DROP TABLE IF EXISTS phrases")
+    c.execute("""CREATE TABLE phrases(
+              id INTEGER,
+              latin TEXT,
+              english TEXT,
+              notes TEXT,
+              length INTEGER)""")
 
-soup = BeautifulSoup(html, "html.parser")
-list_table = soup.find_all("table", attrs={"class":"wikitable"})
+def fill_database(list_table, c, conn):
+    i = 0 # phrase id
+    print("iterating through tables")
+    for table in list_table:
+        for row in table.tbody.find_all("tr", recursive=False):
+            cell = row.find_all("td", recursive=False)
+            if len(cell) > 2:
+                print(i, end="\r")
 
-output = []
+                latin = (cell[0].get_text(" ", strip=True)).rstrip()
+                english = (cell[1].get_text(" ", strip=True)).rstrip()
+                notes = (cell[2].get_text(" ", strip=True)).rstrip()
+    
+                c.execute("""INSERT INTO phrases
+                         (id, latin, english, notes, length)
+                         VALUES(?, ?, ?, ?, ?)""",
+                         (i, latin, english, notes, len(latin)))
+                conn.commit()
+            i = i + 1
 
-for table in list_table:
-    for row in table.find_all("tr")[1:]:
-        cell = row.find_all("td")
-        for content in cell:
-            text = content.get_text()
-            output.append(text)
+def get_tables():
+    url = ("""https://en.wikipedia.org/w/index.php?title=List_of_Latin_phrases_(
+          full)&oldid=986793908""")
+    return get_html(url).find_all("table", attrs={"class":"wikitable"})
 
-print(output)
+def main(args):
+    conn = sqlite3.connect(args.output)
+    c = conn.cursor()
+    prep_database(c)
+    fill_database(get_tables(), c, conn)
 
+if __name__ == "__main__":
+    main(parse_args())